# Instructor-Worker Large Language Model System for Policy Recommendation: a Case Study on Air Quality Analysis of the January 2025 Los Angeles Wildfires

arXiv: https://arxiv.org/abs/2503.00566 · HTML: https://mlsanity.com/paper/2503.00566/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 41 references that are in the map.
- First posted on arXiv 1 Mar 2025.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling](https://mlsanity.com/paper/2412.15084/) (2024)
- [AirFormer: Predicting Nationwide Air Quality in China with Transformers](https://mlsanity.com/paper/2211.15979/) (2022)
- [Autonomous GIS: the next-generation AI-powered GIS](https://mlsanity.com/paper/2305.06453/) (2023)
- [An LLM Agent for Automatic Geospatial Data Analysis](https://mlsanity.com/paper/2410.18792/) (2024)
- [Enhanced 3D Urban Scene Reconstruction and Point Cloud Densification using Gaussian Splatting and Google Earth Imagery](https://mlsanity.com/paper/2405.11021/) (2024)
- [A Deep Learning Approach for Forecasting Air Pollution in South Korea Using LSTM](https://mlsanity.com/paper/1804.07891/) (2018)
- [VayuBuddy: an LLM-Powered Chatbot to Democratize Air Quality Insights](https://mlsanity.com/paper/2411.12760/) (2024)
- [Gaussian Building Mesh (GBM): Extract a Building's 3D Mesh with Google Earth and Gaussian Splatting](https://mlsanity.com/paper/2501.00625/) (2024)
- [Digital Twin Buildings: 3D Modeling, GIS Integration, and Visual Descriptions Using Gaussian Splatting, ChatGPT/Deepseek, and Google Maps Platform](https://mlsanity.com/paper/2502.05769/) (2025)

## Built on by (most cited first, 6 of 6)

- [Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications](https://mlsanity.com/paper/2507.00914/) (2025)
- [Forecasting and Visualizing Air Quality from Sky Images with Vision-Language Models](https://mlsanity.com/paper/2509.15076/) (2025)
- [Context-Aware Visual Prompting: Automating Geospatial Web Dashboards with Large Language Models and Agent Self-Validation for Decision Support](https://mlsanity.com/paper/2511.20656/) (2025)
- [Risk-Aware LLM Agents for Geospatial Data Retrieval: Design and Preliminary Adversarial Evaluation](https://mlsanity.com/paper/2606.15077/) (2026)
- [Securing Multi-Agent GIS Systems: Risk Evaluation and Prompt Hardening Optimization](https://mlsanity.com/paper/2606.17092/) (2026)
- [Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing](https://mlsanity.com/paper/2606.22496/) (2026)

## Abstract (arXiv)

The Los Angeles wildfires of January 2025 caused more than 250 billion dollars in damage and lasted for nearly an entire month before containment. Following our previous work, the Digital Twin Building, we modify and leverage the multi-agent large language model framework as well as the cloud-mapping integration to study the air quality during the Los Angeles wildfires. Recent advances in large language models have allowed for out-of-the-box automated large-scale data analysis. We use a multi-agent large language system comprised of an Instructor agent and Worker agents. Upon receiving the users' instructions, the Instructor agent retrieves the data from the cloud platform and produces instruction prompts to the Worker agents. The Worker agents then analyze the data and provide summaries. The summaries are finally input back into the Instructor agent, which then provides the final data analysis. We test this system's capability for data-based policy recommendation by assessing our Instructor-Worker LLM system's health recommendations based on air quality during the Los Angeles wildfires.